© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Llama3.1-8B-IT
    7. Resid Post - 131k
    9. 15-RESID-POST-AA
    11. 128025
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_15/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    tober
    -0.07
     näch
    -0.06
     mooie
    -0.06
    gether
    -0.06
     nic
    -0.06
     qualité
    -0.06
    tanggal
    -0.06
     realities
    -0.06
    asers
    -0.06
    “So
    -0.06
    POSITIVE LOGITS
     exploiting
    0.07
     注意
    0.06
    %!
    0.06
    732
    0.06
     CUSTOM
    0.06
    employed
    0.06
    :invoke
    0.06
     Clara
    0.06
    fcn
    0.06
    .arch
    0.06
    Activations Density 0.000%

    No Known Activations